Agent skill
collab-canvas
Install this agent skill to your Project
npx add-skill https://github.com/collaborator-ai/collab-public/tree/main/collab-electron/packages/collab-canvas-skill/skills/collab-canvas
SKILL.md
Collaborator Canvas
Control Collaborator's spatial canvas from the terminal using the collab-canvas CLI.
The canvas is a pannable, zoomable surface where tiles display terminals, files, images, and graphs.
Coordinate System
All positions and sizes use grid units. One grid unit = 20 pixels. Origin (0,0) is the top-left corner. X increases rightward, Y increases downward.
Tile Types
| Type | Use for | Default size (w x h) |
|---|---|---|
term |
Terminal / shell session | 20 x 25 |
note |
Markdown files (.md) | 22 x 27 |
code |
Source code files | 22 x 27 |
image |
Images (.png, .jpg, .gif, .webp) | 14 x 14 |
graph |
.graph.json or folder graphs | 30 x 25 |
Type is inferred from the file when --file is used:
.md,.txt->note.graph.json->graph.png,.jpg,.gif,.svg,.webp->image- Directories ->
graph - Everything else ->
code
Commands
collab-canvas tile list
List all tiles on the canvas. Returns JSON array with id, type, position, size, and file path for each tile.
collab-canvas tile list
collab-canvas tile create
Create a new tile on the canvas.
collab-canvas tile create <type> [--file <path>] [--pos x,y] [--size w,h]
<type>: term, note, code, image, or graph--file <path>: file to display (required for note, code, image, graph; omit for term)--pos x,y: position in grid units (default: viewport center)--size w,h: size in grid units (default: per-type default above)
Returns the new tile's ID on stdout.
Examples:
# Open a terminal at position (5, 5)
collab-canvas tile create term --pos 5,5
# Open a markdown file with default placement
collab-canvas tile create note --file ./README.md
# Open a graph file at a specific position and size
collab-canvas tile create graph --file ./entities.graph.json --pos 25,0 --size 35,30
collab-canvas tile rm
Remove a tile from the canvas.
collab-canvas tile rm <id>
collab-canvas tile move
Reposition a tile.
collab-canvas tile move <id> --pos x,y
collab-canvas tile resize
Resize a tile.
collab-canvas tile resize <id> --size w,h
collab-canvas tile focus
Pan and zoom the viewport to bring one or more tiles into view, then flash their focus rings.
collab-canvas tile focus <id> [<id>...]
Examples:
# Focus a single tile
collab-canvas tile focus tile-abc123
# Focus multiple tiles (viewport zooms to fit all)
collab-canvas tile focus tile-abc123 tile-def456
collab-canvas terminal write
Send input to a terminal tile. The tile must be of type term with an active PTY session.
collab-canvas terminal write <id> <input>
Examples:
# Run a command in a terminal tile
collab-canvas terminal write tile-abc123 $'ls -la\n'
# Launch Claude Code in headless JSON mode
collab-canvas terminal write tile-abc123 $'claude -p "fix the bug" --output-format json\n'
collab-canvas terminal read
Read recent output from a terminal tile. Returns raw terminal output from the PTY session's ring buffer.
collab-canvas terminal read <id> [--lines N]
--lines N: number of lines to capture (default: 50)
Composition Patterns
Side-by-side comparison
Two files next to each other for comparison.
collab-canvas tile create code --file ./old.ts --pos 0,0
collab-canvas tile create code --file ./new.ts --pos 23,0
Research workspace
Knowledge graph on the left, notes on the right, terminal below.
collab-canvas tile create graph --file ./research.graph.json --pos 0,0 --size 30,25
collab-canvas tile create note --file ./notes.md --pos 31,0
collab-canvas tile create term --pos 0,26
Dashboard layout
Multiple views arranged in a grid.
collab-canvas tile create graph --file ./entities.graph.json --pos 0,0 --size 30,25
collab-canvas tile create note --file ./log.md --pos 31,0
collab-canvas tile create note --file ./report.md --pos 31,14
collab-canvas tile create term --pos 0,26
Focus view
Single tile centered with generous size.
collab-canvas tile create code --file ./main.ts --pos 5,2 --size 40,35
Agent in a terminal
Launch a Claude Code instance in a terminal tile for the human to observe.
# Create terminal, wait for PTY, then launch agent
collab-canvas tile create term --pos 0,0
# (use tile list to get the tile ID, then)
collab-canvas terminal write <id> $'claude -p "summarize this project" --output-format json\n'
# Read the result when done
collab-canvas terminal read <id> --lines 100
Conventions
- Always
tile listfirst to see what's already on the canvas before creating tiles. - Use
tile focusto frame after arranging tiles so the user can see them. - Clean up when done: remove tiles you created when they're no longer needed.
- Leave 1 grid unit gap between adjacent tiles for visual clarity.
- File tiles auto-refresh: when you write to a file that has a tile, the tile updates automatically. No need to close and reopen.
- Graph tiles support incremental updates: append nodes to a
.graph.jsonfile and the graph tile smoothly incorporates them. - Terminal tiles need time to initialize: after
tile create term, wait a few seconds beforeterminal writeso the PTY session can start.
Setup
The collab-canvas CLI is installed to ~/.local/bin/. If the command is not found, the user needs to add it to their PATH:
export PATH="$HOME/.local/bin:$PATH"
Add this to ~/.zshrc (macOS) or ~/.bashrc (Linux) to persist across sessions.
Exit Codes
| Code | Meaning |
|---|---|
| 0 | Success |
| 1 | RPC error (tile not found, invalid params) |
| 2 | Connection failure (Collaborator not running) |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Didn't find tool you were looking for?